Keep the stats of unhealty replica and add the timeline info

dalibo · Sep 28, 2023 · ea8541d · ea8541d
1 parent cee0ff8
commit ea8541d
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 7 deletions.
diff --git a/check_patroni/cli.py b/check_patroni/cli.py
@@ -378,6 +378,7 @@ def cluster_has_replica(
         ),
         nagiosplugin.ScalarContext("unhealthy_replica"),
         nagiosplugin.ScalarContext("replica_lag"),
+        nagiosplugin.ScalarContext("replica_timeline"),
         nagiosplugin.ScalarContext("replica_sync"),
     )
     check.main(verbose=ctx.obj.verbose, timeout=ctx.obj.timeout)

diff --git a/check_patroni/cluster.py b/check_patroni/cluster.py
@@ -129,6 +129,14 @@ def probe(self: "ClusterHasReplica") -> Iterable[nagiosplugin.Metric]:
         # Look for replicas
         for member in cluster_item_dict["members"]:
             if member["role"] in ["replica", "sync_standby"]:
+                replicas.append(
+                    {
+                        "name": member["name"],
+                        "lag": member["lag"],
+                        "timeline": member["timeline"],
+                        "sync": 1 if member["role"] == "sync_standby" else 0,
+                    }
+                )
                 if (
                     (has_streaming_state and member["state"] == "streaming")
                     or (
@@ -137,13 +145,6 @@ def probe(self: "ClusterHasReplica") -> Iterable[nagiosplugin.Metric]:
                         and member["timeline"] == leader_tl
                     )
                 ) and member["lag"] != "unknown":
-                    replicas.append(
-                        {
-                            "name": member["name"],
-                            "lag": member["lag"],
-                            "sync": 1 if member["role"] == "sync_standby" else 0,
-                        }
-                    )
 
                     if member["role"] == "sync_standby":
                         sync_replica += 1
@@ -163,6 +164,9 @@ def probe(self: "ClusterHasReplica") -> Iterable[nagiosplugin.Metric]:
             yield nagiosplugin.Metric(
                 f"{replica['name']}_lag", replica["lag"], context="replica_lag"
             )
+            yield nagiosplugin.Metric(
+                f"{replica['name']}_timeline", replica["timeline"], context="replica_timeline"
+            )
             yield nagiosplugin.Metric(
                 f"{replica['name']}_sync", replica["sync"], context="replica_sync"
             )